已发表成果:
WOK 论文 226 篇;中文核心 9 篇;专利发明 8 个;
                                    
IMC-Det: Intra-Inter Modality Contrastive Learning for Video Object Detection
                                    
                                
                                    
Wavelet-domain feature decoupling for weakly supervised multi-object tracking
                                    
                                
                                    
Unpaired Caricature-Visual Face Recognition via Feature Decomposition-Restoration-Decomposition
                                    
                                
                                    
Transitive Vision-Language Prompt Learning for Domain Generalization
                                    
                                
                                    
Dynamically Anchored Prompting for Task-Imbalanced Continual Learning
                                    
                                
                                    
Spatial-Contextual Discrepancy Information Compensation for GAN Inversion
                                    
                                
                                    
Federated Learning with Extremely Noisy Clients via Negative Distillation
                                    
                                
                                    
Combating Label Noise by Uncertainty-Aware Neighborhood Sample Selection
                                    
                                
                                    
Frequency Domain Nuances Mining for Visible-Infrared Person Re-identification
                                    
                                
                                    
Explicit State Representation Guided Video-based Pedestrian Attribute Recognition
                                    
                                
                                    
BI-DIRECTIONAL MOTION ATTENTION WITH CONTRASTIVE LEARNING FOR FEW-SHOT ACTION RECOGNITION
                                    
                                
                                    
Second-Order Proximity Guided Sampling Consensus for Robust Model Fitting
                                    
                                
                                    
Cross-Modal Contrastive Learning Network for Few-Shot Action Recognition
                                    
                                
                                    
Robust Heterogeneous Model Fitting for Multi-source Image Correspondences
                                    
                                
                                    
Visual-Textual Attribute Learning for Class-Incremental Facial Expression Recognition
                                    
                                
                                    
Relationship-Guided Knowledge Transfer for Class-Incremental Facial Expression Recognition
                                    
                                
                                    
Few-Shot Action Recognition via Multi-View Representation Learning
                                    
                                
                                    
Multi-Stage Network With Geometric Semantic Attention for Two-View Correspondence Learning
                                    
                                
                                    
An Effective Visible-Infrared Person Re-identification Network Based on?Second-Order Attention and?Mixed Intermediate Modality
                                    
                                
                                    
Cascaded-Scoring Tracklet Matching for Multi-object Tracking
                                    
                                
                                    
An Effective Dynamic Reweighting Method for Unbiased Scene Graph Generation
                                    
                                
                                    
Joint Relation Modeling and Feature Learning for Class-Incremental Facial Expression Recognition
                                    
                                
                                    
DeCAB: Debiased Semi-supervised Learning for Imbalanced Open-Set Data
                                    
                                
                                    
Spatio-Temporal Self-supervision for Few-Shot Action Recognition
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Preface
                                    
                                
                                    
Dual-Mode Learning for Multi-Dataset X-Ray Security Image Detection